A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration

Thomas Pock; Martin Urschler; Christopher Zach; Reinhard Beichel; Horst Bischof

doi:10.1007/978-3-540-75759-7_62

Back

A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration

Book chapter

Open access

Peer reviewed

A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration

Thomas Pock, Martin Urschler, Christopher Zach, Reinhard Beichel and Horst Bischof

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007, pp.511-518

Lecture Notes in Computer Science, 4792, Springer Berlin Heidelberg

2007

DOI: 10.1007/978-3-540-75759-7_62

Files and links (1)

url

https://doi.org/10.1007/978-3-540-75759-7_62View

Published (Version of record) Open Access

Abstract

Nonlinear image registration is a challenging task in the field of medical image analysis. In many applications discontinuities may be present in the displacement field, and intensity variations may occur. In this work we therefore utilize an energy functional which is based on Total Variation regularization and a robust data term. We propose a novel, fast and stable numerical scheme to find the minimizer of this energy. Our approach combines a fixed-point procedure derived from duality principles combined with a fast thresholding step. We show experimental results on synthetic and clinical CT lung data sets at different breathing states as well as registration results on inter-subject brain MRIs.

Breathing Motion

Image Pyramid

Image Registration

Medical Image Analysis

Normalize Mutual Information

Details

Title: Subtitle: A Duality Based Algorithm for TV-L1-Optical-Flow Image Registration
Creators: Thomas Pock - Institute for Computer Graphics & Vision, Graz University of Technology, Austria
Martin Urschler - Institute for Computer Graphics & Vision, Graz University of Technology, Austria
Christopher Zach - VRVis Research Centre, Graz, Austria
Reinhard Beichel - University of Iowa, Electrical and Computer Engineering
Horst Bischof - Institute for Computer Graphics & Vision, Graz University of Technology, Austria
Resource Type: Book chapter
Publication Details: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007, pp.511-518
Series: Lecture Notes in Computer Science; 4792
DOI: 10.1007/978-3-540-75759-7_62
eISSN: 1611-3349
ISSN: 0302-9743
Publisher: Springer Berlin Heidelberg; Berlin, Heidelberg
Language: English
Date published: 2007
Academic Unit: Electrical and Computer Engineering
Record Identifier: 9984197074602771

Metrics

32 Record Views